Display Field-Of-View Agnostic Robust CT Kernel Synthesis Using Model-Based Deep Learning

TL;DR

This paper presents a model-based deep learning approach for robust, display field-of-view agnostic CT kernel synthesis that improves efficiency and consistency across different DFOVs in clinical imaging.

Contribution

It introduces a novel, DFOV-agnostic kernel synthesis method that explicitly incorporates CT kernel and DFOV characteristics into the deep learning model.

Findings

The method achieves real-time kernel synthesis performance.

It outperforms direct learning networks in robustness to DFOV variations.

Experimental validation on clinical and phantom data confirms effectiveness.

Abstract

In X-ray computed tomography (CT) imaging, the choice of reconstruction kernel is crucial as it significantly impacts the quality of clinical images. Different kernels influence spatial resolution, image noise, and contrast in various ways. Clinical applications involving lung imaging often require images reconstructed with both soft and sharp kernels. The reconstruction of images with different kernels requires raw sinogram data and storing images for all kernels increases processing time and storage requirements. The Display Field-of-View (DFOV) adds complexity to kernel synthesis, as data acquired at different DFOVs exhibit varying levels of sharpness and details. This work introduces an efficient, DFOV-agnostic solution for image-based kernel synthesis using model-based deep learning. The proposed method explicitly integrates CT kernel and DFOV characteristics into the forward model. Experimental results on clinical data, along with quantitative analysis of the estimated modulation transfer function using wire phantom data, clearly demonstrate the utility of the proposed method in real-time. Additionally, a comparative study with a direct learning network, that lacks forward model information, shows that the proposed method is more robust to DFOV variations.